activity
20182024
most citedExplaining and Interpreting LSTMs

74 citations · 74 across the 4 of their papers we have counts for

collaborators

7 papers

cs.LG2024

Pretraining Graph Transformers with Atom-in-a-Molecule Quantum Properties for Improved ADMET Modeling

Alessio Fallani, Ramil Nugmanov, Jose Arjona-Medina +3

We evaluate the impact of pretraining Graph Transformer architectures on atom-level quantum-mechanical features for the modeling of absorption, distribution, metabolism, excretion,…

cs.LG2024

Analysis of Atom-level pretraining with Quantum Mechanics (QM) data for Graph Neural Networks Molecular property models

Jose Arjona-Medina, Ramil Nugmanov

Despite the rapid and significant advancements in deep learning for Quantitative Structure-Activity Relationship (QSAR) models, the challenge of learning robust molecular represent…

cs.LG2022

MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling

Julius Ott, Lorenzo Servadei, Jose Arjona-Medina +7

Data selection is essential for any data-based optimization technique, such as Reinforcement Learning. State-of-the-art sampling strategies for the experience replay buffer improve…

cs.LG2020

Convergence Proof for Actor-Critic Methods Applied to PPO and RUDDER

Markus Holzleitner, Lukas Gruber, José Arjona-Medina +2

We prove under commonly used assumptions the convergence of actor-critic reinforcement learning algorithms, which simultaneously learn a policy function, the actor, and a value fun…

cs.LG2020

Align-RUDDER: Learning From Few Demonstrations by Reward Redistribution

Vihang P. Patil, Markus Hofmarcher, Marius-Constantin Dinu +5

Reinforcement learning algorithms require many samples when solving complex hierarchical tasks with sparse and delayed rewards. For such complex tasks, the recently proposed RUDDER…

cs.LG2019★ 74 cited

Explaining and Interpreting LSTMs

Leila Arras, Jose A. Arjona-Medina, Michael Widrich +5

While neural networks have acted as a strong unifying force in the design of modern AI systems, the neural network architectures themselves remain highly heterogeneous due to the v…